Enregistré dans:
Détails bibliographiques
Auteurs principaux: Panariello, Michele, Todisco, Massimiliano, Evans, Nicholas
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.04306
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911982193475584
author Panariello, Michele
Todisco, Massimiliano
Evans, Nicholas
author_facet Panariello, Michele
Todisco, Massimiliano
Evans, Nicholas
contents Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content should be preserved. There is always a trade-off; all approaches reported thus far sacrifice spoken content for anonymisation performance. We report what is, to the best of our knowledge, the first attempt to actively preserve spoken content in voice anonymisation. We show how the output of an auxiliary automatic speech recognition model can be used to condition the vocoder module of an anonymisation system using a set of learnable embedding dictionaries in order to preserve spoken content. Relative to a baseline approach, and for only a modest cost in anonymisation performance, the technique is successful in decreasing the word error rate computed from anonymised utterances by almost 60%.
format Preprint
id arxiv_https___arxiv_org_abs_2408_04306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Preserving spoken content in voice anonymisation with character-level vocoder conditioning
Panariello, Michele
Todisco, Massimiliano
Evans, Nicholas
Audio and Speech Processing
Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content should be preserved. There is always a trade-off; all approaches reported thus far sacrifice spoken content for anonymisation performance. We report what is, to the best of our knowledge, the first attempt to actively preserve spoken content in voice anonymisation. We show how the output of an auxiliary automatic speech recognition model can be used to condition the vocoder module of an anonymisation system using a set of learnable embedding dictionaries in order to preserve spoken content. Relative to a baseline approach, and for only a modest cost in anonymisation performance, the technique is successful in decreasing the word error rate computed from anonymised utterances by almost 60%.
title Preserving spoken content in voice anonymisation with character-level vocoder conditioning
topic Audio and Speech Processing
url https://arxiv.org/abs/2408.04306